feat(api): 叙事 prompt、职业上下文、读路径章节、WS 解耦与错误脱敏

- 回忆录：事实边界补充允许清单；传记文体示例与 JSON 叙事要求对齐
- default 职业提示 occupation_context；cadre/military 退休语境
- GET 章节读路径零写入，prepare_chapter_read_view + markdown_for_response
- 文本归一抽到 core/text_normalize；移除弃用 reply 策略与 recompose_chapters_for_story
- ConversationService：WS 连接/用户段落/结束对话；对外错误固定文案
- 测试：HTTP 脱敏契约、章节读视图、occupation 与 background_voice

api/tests/test_oral_normalize.py

@@ -2,24 +2,22 @@
 
 from unittest.mock import patch
 
-from app.features.memoir.oral_normalize import (
-    apply_oral_normalization_rules,
-    normalize_oral_for_memoir,
-)
+from app.core.text_normalize import apply_oral_rules
+from app.features.memoir.oral_normalize import normalize_oral_for_memoir
 
 
 def test_apply_rules_mei_kanshang_wo() -> None:
-    assert "没看上我" in apply_oral_normalization_rules("我去试镜了 美看上我 张伟")
+    assert "没看上我" in apply_oral_rules("我去试镜了 美看上我 张伟")
 
 
 def test_apply_rules_mei_kanshang_ni() -> None:
-    assert apply_oral_normalization_rules("美看上你") == "没看上你"
+    assert apply_oral_rules("美看上你") == "没看上你"
 
 
 def test_apply_rules_no_false_positive_rong() -> None:
     """「美容」等不应被误替换。"""
     s = "我去了解美容项目"
-    assert apply_oral_normalization_rules(s) == s
+    assert apply_oral_rules(s) == s
 
 
 def test_normalize_respects_global_off() -> None: